Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3923 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7986. Min Act: -0.0001

Data Index: 260116 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7115. Min Act: -0.0001

Data Index: 415879 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6715. Min Act: -0.0001

Data Index: 174493 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7063. Min Act: -0.0001

Data Index: 692379 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6029. Min Act: -0.0001

Data Index: 444165 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1085877 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6276. Min Act: -0.0001

Data Index: 115209 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6275. Min Act: -0.0001

Data Index: 1132237 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1020368 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6023. Min Act: -0.0001

Data Index: 1024033 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6335. Min Act: -0.0001

Data Index: 767875 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5852. Min Act: -0.0001

Data Index: 202711 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5685. Min Act: -0.0001

Data Index: 350108 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5791. Min Act: -0.0001

Data Index: 210973 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5468. Min Act: -0.0001

Data Index: 757731 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5497. Min Act: -0.0001

Data Index: 617389 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5418. Min Act: -0.0001

Data Index: 241658 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5667. Min Act: -0.0001

Data Index: 982221 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5752. Min Act: -0.0001

Data Index: 240484 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5179. Min Act: -0.0001

Data Index: 179742 (C4 (Web Text))

Max Activating Token Index: 218